Qualcomm-AI-research / FrameExit
☆34Updated 3 years ago
Alternatives and similar repositories for FrameExit
Users that are interested in FrameExit are comparing it to the libraries listed below
Sorting:
- Reducing spatial redundancy in video recognition. SOTA computational efficiency.☆124Updated 5 months ago
- Learning Representational Invariances for Data-Efficient Action Recognition☆33Updated 3 years ago
- Video Contrastive Learning with Global Context, ICCVW 2021☆158Updated 2 years ago
- ☆76Updated 3 years ago
- [ECCV2020] Learn optimal resolution and skipping mechanism for efficient video understanding☆61Updated 4 years ago
- Code accompanying Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos (CVPR 2021)☆33Updated 3 years ago
- ☆35Updated 3 years ago
- ☆16Updated 4 years ago
- [AAAI 2020] Temporal Interlacing Network☆84Updated 4 years ago
- super image for action recognition☆55Updated 3 years ago
- ☆44Updated 4 years ago
- code base for vision transformers☆36Updated 3 years ago
- A library of transformer models for computer vision and multi-modality research☆49Updated 3 years ago
- A single stage temporal action detection toolbox based on PyTorch☆53Updated 3 years ago
- [ICLR2021] AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition☆34Updated 4 years ago
- ☆31Updated 3 years ago
- [CVPR 2021] 3D CNNs with Adaptive Temporal Feature Resolutions https://arxiv.org/abs/2011.08652☆26Updated 3 years ago
- cuda implementation of depthwise conv3d☆22Updated 3 years ago
- Code for Temporal Data Augmentations (ECCVW 2020)☆36Updated 4 years ago
- ☆71Updated 4 years ago
- Video Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.☆48Updated 4 years ago
- code for our ECCV-2020 paper: Self-supervised Video Representation Learning by Pace Prediction☆99Updated 4 years ago
- Code and models for the paper Glance-and-Gaze Vision Transformer☆28Updated 3 years ago
- Official Code Release for Container : Context Aggregation Network☆46Updated 3 years ago
- The official Codes for NeurIPS 2019 paper. Quanfu Fan, Ricarhd Chen, Hilde Kuehne, Marco Pistoia, David Cox, "More Is Less: Learning Effi…☆53Updated 4 years ago
- Rethinking Self-Supervised Correspondence Learning: A Video Frame-level Similarity Perspective, in ICCV 2021 (Oral)☆146Updated 3 years ago
- Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation, ECCV 2020 Oral☆71Updated 4 years ago
- ☆25Updated 3 years ago
- Code for our CVPR 2021 paper "Coarse-Fine Networks for Temporal Activity Detection in Videos"☆57Updated 3 years ago
- [ECCV 2020] Boundary-Aware Cascade Networks for Temporal Action Segmentation☆84Updated 4 years ago